Agent-Body
Agent frameworksA plugin layer for DeepSeek Harness that routes intent to tools, gates unused tool schemas, and adds persistent memory, event-triggered reflexes, and recovery behavior.
Explore ways to carry useful context between agent sessions. Decide what should be remembered, how it can be corrected, and when it should be forgotten before choosing a storage layer.
A plugin layer for DeepSeek Harness that routes intent to tools, gates unused tool schemas, and adds persistent memory, event-triggered reflexes, and recovery behavior.
ContextStream is an MCP server for shared project context and persistent agent memory, with semantic search, traceable sources, and scoped access.
An OpenClaw-based multi-agent workforce framework with shared team memory, goal decomposition, fleet learning, task management, and approval workflows.
A local-first memory tool for AI coding assistants that captures project context and carries it across sessions.
An OpenCode-based runtime for scheduled, persistent subagents, each with an isolated workspace, plus fleet status, streaming logs, retries, and restart handling.
Hermes Agent is an open-source agent from Nous Research that runs in a terminal and through messaging platforms, keeps memory and creates skills from experience, and works with the model provider of your choice.
Hyperconsciousness is an MIT-licensed developer alpha Rust knowledge store for humans and AI agents that keeps signed, encrypted, append-only records and exposes scoped, expiring retrieval and capture grants through CLI, MCP and HTTP.
kith gives multi-agent systems relationship memory: agents record scoped observations and derive trust, reliability, sentiment, and capability views with provenance.
Add persistent memory to agents across sessions, tools and runs.
A persistent memory tool for AI coding agents that isolates workspaces by project and provides a dashboard for reviewing and managing stored context.
MemGPT introduces a customizable AI chatbot framework with self-editing memory and access to unlimited data, promoting perpetual, context-rich conversations
Mnemoverse is an open-source MCP server for persistent AI-agent memory, with feedback tools that adjust how memories are ranked.
An open-source semantic search runtime for conversational AI agents, combining vector and keyword retrieval, built-in embeddings, metadata filters, and browser WebAssembly support.
An open-source AI team workspace for persistent agent identity and memory, multi-agent collaboration, and long-running work across connected channels.
A local-first, cross-model memory system that helps AI agents retain context, coordinate, and learn between sessions.
Open Index is a self-hosted context layer for domain-specialized AI agents, building searchable knowledge graphs with structured schemas, semantic search, and MCP read/write access.
OpenBot is an open-source self-hosted platform for running a team of persistent AI bots that wake on incoming messages, use shell, HTTP, custom Python and MCP tools, keep long term memory, and pause for human approval.
Remembra is a self-hosted semantic memory system for AI agents, with persistent memory, retrieval, knowledge graph features, and integrations for agent frameworks and MCP.
Separate task state, user preferences and source documents, then choose storage, retrieval and deletion rules for each type of information.
Read the guide